# Step 3.7 Flash

Most cost-effective multimodal model. 198B total, ~11B active (sparse MoE). Supports vision + video input with tunable reasoning tiers.

## Overview

- **Provider:** StepFun
- **Model ID:** `step-3.7-flash`
- **Type:** Chat
- **Canonical URL:** https://modelstack.cc/models/chat/step-3.7-flash
- **Version:** 3.7 Flash
- **Best for:** Multimodal analysis, agentic workflows, coding tasks, cost optimization

## Pricing

| Usage | Price |
| --- | ---: |
| Input | $0.2 / 1M tokens |
| Output | $1.15 / 1M tokens |
| Cache read | $0.04 / 1M tokens |
| Cache write (5 minutes) | $0.2 / 1M tokens |

## Specifications

- **Context window:** 256K
- **Maximum output:** 256K
- **Typical latency:** 10 ms
- **Released:** 2026-02

## Capabilities

- chat
- tool_use
- coding

## API usage

Use this model ID in a ModelStack API request:

```json
{
  "model": "step-3.7-flash"
}
```

For the rendered page, visit https://modelstack.cc/models/chat/step-3.7-flash.